Dong Gong

Picture of Dong Gong 

I am a Senior Lecturer and ARC DECRA Fellow at the School of Computer Science and Engineering, The University of New South Wales (UNSW Sydney), Australia. I am also an Adjunct Lecturer with the Australian Institute for Machine Learning (AIML) of The University of Adelaide. Before joining UNSW in 2022, I was a Research Fellow at the Australian Institute for Machine Learning (AIML), a Principal Researcher at Centre for Augmented Reasoning (CAR), The University of Adelaide, working with Prof. Anton van den Hengel, Prof. Qinfeng (Javen) Shi and Prof. Chunhua Shen. I obtained my PhD and B.S. in computer science from Northwestern Polytechnical University in 2018 and 2012, advised by Prof. Yanning Zhang. During my PhD studies, I spent two years at The University of Adelaide, working with Javen and Anton.

I am continually seeking highly motivated PhD, MPhil, or visiting students with passion and background for computer vision and machine learning.
Please check the details and drop me an email with your CV and transcripts if you are interested.

[Github] [Google Scholar] [Twitter] [UNSW Homepage]

News

  • (Jan  2024) 2 papers (on OOD detection and causal representation learning) accepted to appear at ICLR 2024. Congrats to Haodong and Yuhang.

  • (Sep  2023) 2 papers (both on Continual Learning) accepted to appear at NeurIPS 2023. Congrats to Saurav and Mark.

  • (May  2023) I am serving as the Tutorial Chair for AJCAI 2023.

  • (Feb  2023) 1 paper (about multi-frame depth estimation) accepted to appear at CVPR 2023

  • (Feb  2023) 1 paper (image deblurring with Transformer) accepted to appear in TIP

  • (Jan  2023) 1 paper accepted to appear at ICLR 2023. Congrats to collaborators.

  • (Sep  2022) I am awarded ARC Discovery Early Career Researcher Award (DECRA) starting in 2023 to study Continual Learning.

  • (Sep  2022) 1 paper (about DAG learning) accepted to appear at NeurIPS 2022

  • (Mar 2022) 1 paper (Continual Learning with Sparse Neural Networks) accepted to appear at CVPR 2022

  • (Jan  2022) Check the article summarizing part of our works using ML to help agriculture innovation.

  • (Sep  2021) 1 paper (about HDR imaging) accepted to appear in IJCV.

  • (July 2021) 1 paper (Memory-augmented Neural Relational Inference) accepted to appear at ICCV 2021

  • (July 2021) I will be a co-lecturer on Introduction to Statistical Machine Learning at UoA this semester, and give guest lectures at Deep Learning Fundamentals.

  • (Dec 2020) 1 paper (unpaired domain-adaptive learning for realistic SR) accepted to appear in TIP

  • (Oct  2020) 1 paper (learning attention model for vehicle retrieval) accepted to appear in TITS

  • (Sep  2020) I am giving lectures at UoA Deep Learning Fundamentals on RNN, Attention, & Memory Networks.

  • (July 2020) 1 paper (memory network for 3D point cloud with long-tail dist.) accepted to appear at ECCV 2020

  • (Jan  2020) 1 paper (on learning to optimize for image deconv.) accepted to appear in TNNLS

  • (July 2019) 1 paper (MemAE) accepted to appear at ICCV 2019

  • (July 2019) 1 paper (about Sparse PCA) accepted to appear in TKDE

  • (Jun  2019) 2nd Prize of OZ Minerals Explorer Challenge as part of DeepSightX team

  • (Mar 2019) 1 paper accepted to appear in TKDE

  • (Feb  2019) 4 papers accepted to appear at CVPR 2019

  • (Nov 2018) 1 paper (on Blind Image Quality Assessment) accepted to appear in TIP

  • (Oct  2018) 1 paper (about MRF based Compressive Sensing) accepted to appear in TIP

  • (Sep  2018) 1 paper (MPTV) accepted to appear in TIP

  • (July 2018) 2 papers accepted to appear at ECCV 2018

  • (Oct  2017) Participated in ICCV 2017 Doctoral Consortium with a travel award

  • (July 2017) 1 paper accepted to appear at ICCV 2017

  • 1 paper accepted to appear at CVPR 2017

  • 1 new arXiv paper on deep learning for motion estimation and blur removal

  • 1 paper accepted to appear at AAAI 2017 as an oral

Research Interests

I have broad interests in machine learning and computer vision. My current major research topics are about:

  • learning with non-ideal supervision in real-world scenarios, e.g.,
    - continual learning
    - unsupervised/semi-supervised/domain-adaptive learning

  • low/high-level computer vision

  • deep/sparse modeling, optimization and learning, e.g.,
    - memory mechanism in deep learning
    - deep learning with sparsity

  • interdisciplinary problems with of CV, ML, and DL technologies

Contact

Office: Level 4, Building K17, UNSW, Sydney 2052, Australia

Email : edgong01 at gmail.com, dong.gong at unsw.edu.au